Skip to main content
Glama

Edit a tree you are holding

edit_nodes
Read-onlyIdempotent

Apply edit ops to a node tree you pass IN, and get the edited tree back. Nothing is saved and no project is touched — this is the unsaved counterpart to edit_project. Use it to change a model you are still working on without re-sending the whole tree every time: add a node, cut a hole, group parts, wrap a modifier, then feed the result straight to evaluate, print_check or export. Target nodes by their id; a node you send keeps the id you gave it, and one you omit an id for gets one back in the result, so a later call can name it. Unlike edit_project this is FORGIVING: an op that cannot be applied is skipped and reported in skipped rather than failing the whole call, because nothing here is written and a nearly-right tree beats none; what your nodes lost the same way is in treeWarnings. Same ops as edit_project — read owlcad://schema/edit-ops for what each op requires (this tool’s ops carry no schema of their own), and owlcad://schema/primitives for the node vocabulary an addNode carries.

Input Schema

NameRequiredDescriptionDefault
opsYesEdits to apply in order, each against the result of the last. Up to 40. Same shape as edit_project's.
nodesYesParametric node tree. mm, Z-up, rotations in DEGREES (a rotation.* binding: radians). Read owlcad://schema/primitives for every primitive, modifier and generator and its parameter ranges (unknown params are dropped silently), and owlcad://schema/conventions for the placement arithmetic, which is where most models go wrong.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / nodes / items / properties / generatorKey / description
      Previous value: -"Generator to expand (kind=generator). PREFER one over hand-building the same thing — they carry standards dimensions and solve fits a tree of primitives gets subtly wrong: gearTrain · planetary · rackPinion · wormDrive · herringbone · herringboneTrain · pulley · bearing · belt · spring · adapter · boardMount · enclosure · gridfinity · threadedJar · pinHinge · snapFit · ballSocket · fastener · textPlate · fitCoupon · calibrationBlock · clamp · impeller · axialFan · fanFrame · plugCap · pillowBlock."New value: +"Generator to expand (kind=generator). PREFER one over hand-building the same thing — they carry standards dimensions and solve fits a tree of primitives gets subtly wrong: gearTrain · planetary · rackPinion · wormDrive · bevelPair · herringbone · herringboneTrain · pulley · bearing · belt · spring · adapter · boardMount · enclosure · gridfinity · threadedJar · pinHinge · snapFit · ballSocket · fastener · textPlate · fitCoupon · calibrationBlock · clamp · impeller · axialFan · fanFrame · plugCap · pillowBlock."
  2. Changed1 schema field changed
    • changedInput schema / properties / nodes / description
      Previous value: -"Parametric node tree. mm, Z-up, rotations in DEGREES. Read owlcad://schema/primitives for every primitive, modifier and generator and its parameter ranges (unknown params are dropped silently), and owlcad://schema/conventions for the placement arithmetic, which is where most models go wrong."New value: +"Parametric node tree. mm, Z-up, rotations in DEGREES (a rotation.* binding: radians). Read owlcad://schema/primitives for every primitive, modifier and generator and its parameter ranges (unknown params are dropped silently), and owlcad://schema/conventions for the placement arithmetic, which is where most models go wrong."
  3. Changed1 schema field changed
    • changedInput schema / properties / nodes / items / properties / generatorKey / description
      Previous value: -"Generator to expand (kind=generator). PREFER one over hand-building the same thing — they carry standards dimensions and solve fits a tree of primitives gets subtly wrong: gearTrain · planetary · rackPinion · wormDrive · herringbone · herringboneTrain · pulley · bearing · belt · spring · adapter · boardMount · enclosure · gridfinity · threadedJar · pinHinge · snapFit · ballSocket · fastener · textPlate · fitCoupon · calibrationBlock · clamp · impeller · axialFan · fanFrame · plugCap."New value: +"Generator to expand (kind=generator). PREFER one over hand-building the same thing — they carry standards dimensions and solve fits a tree of primitives gets subtly wrong: gearTrain · planetary · rackPinion · wormDrive · herringbone · herringboneTrain · pulley · bearing · belt · spring · adapter · boardMount · enclosure · gridfinity · threadedJar · pinHinge · snapFit · ballSocket · fastener · textPlate · fitCoupon · calibrationBlock · clamp · impeller · axialFan · fanFrame · plugCap · pillowBlock."
  4. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint), and the description goes well beyond them: it discloses that unresolvable ops are skipped and reported in `skipped` rather than failing the call, that tree-shape losses surface in `treeWarnings`, and that node ids are preserved or auto-assigned so later calls can reference them. That is real behavioural context an agent cannot get from the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and the nothing-is-saved guarantee in the first two clauses, and every sentence carries information that is not duplicated elsewhere. It is dense and long-tailed for a two-parameter tool, with the id/forgiving sentences packed into many clauses, but little is genuinely wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description correctly explains what comes back (`skipped`, `treeWarnings`, ids assigned to unnamed nodes) and delegates the op vocabulary and placement arithmetic to resources. For a tool whose real complexity lives in a referenced schema, this is complete enough to call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the critical `ops` array has no item schema at all, and the description fills that structural gap by pointing to owlcad://schema/edit-ops and owlcad://schema/primitives. It also adds id-retention semantics ('a node you send keeps the id you gave it, and one you omit an id for gets one back') that the schema does not express.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Apply edit ops to a node tree you pass IN, and get the edited tree back') and immediately scopes it as 'the unsaved counterpart to edit_project', so the agent can tell it apart from its closest sibling without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative (edit_project) and the condition that selects this one: use it to change a model 'you are still working on without re-sending the whole tree every time', then feed the result to evaluate, print_check or export. The saved-vs-unsaved distinction is stated outright rather than left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources